© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57395
    Prev
    Next
    INDEX
    Explanations

    key verbs and their conjugations within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reflect
    -0.66
     quæ
    -0.64
    multicolumn
    -0.63
     leçon
    -0.63
     useRouter
    -0.63
    ///</
    -0.62
    ostante
    -0.61
    </caption>
    -0.61
     Heav
    -0.61
     Sodom
    -0.60
    POSITIVE LOGITS
     in
    0.71
    canestro
    0.56
    werve
    0.54
    NameInMap
    0.52
     prop
    0.51
    RenderAtEndOf
    0.50
    lanatory
    0.49
     from
    0.49
     at
    0.49
    θεί
    0.47
    Activations Density 0.026%

    No Known Activations